wav2vec2-xls-r-300m-100e-lg-asr

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.3678
• Wer: 1.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0003
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
14.9517	6.6667	20	5.1569	1.0
4.5284	13.3333	40	3.6413	1.0
3.571	20.0	60	3.6094	1.0
3.2872	26.6667	80	3.5732	1.0
3.1311	33.3333	100	3.4355	1.0
2.9955	40.0	120	3.3223	1.0
2.9259	46.6667	140	3.3184	1.0
2.8683	53.3333	160	3.2794	1.0
2.7513	60.0	180	3.3916	1.0
2.5434	66.6667	200	3.3479	1.0
2.2682	73.3333	220	3.3794	1.0
2.0945	80.0	240	3.3626	1.0
1.9457	86.6667	260	3.3331	1.0
1.8294	93.3333	280	3.3506	1.0
1.7562	100.0	300	3.3678	1.0

Framework versions

• Transformers 4.57.2
• Pytorch 2.9.0+cu126
• Datasets 3.6.0
• Tokenizers 0.22.1